AI Text to Video Generator · MiniMax H3 Max Turbo

Write one scene prompt, choose a 5–15-second integer duration and explicitly select 480P or 768P with MiniMax-H3-Max-Turbo, then receive generated video through a download link. Text alone needs a concrete aspect ratio; image-to-video accepts a first frame and an optional paired last frame.

Your AI

Use with your AI

For tasks with several steps, continue in the AI you already use.

CodexClaude CodeCursorWindsurfCline

View instructions

Use Toolmu Tool minimax-video-h3-max-turbo-minimax, ID 3e9bc4d8-574c-404f-80c6-36e65f039cfc. Use the existing Toolmu connection, or follow https://toolmu.com/SKILL.md to connect when needed. Read this exact Tool’s current input requirements, availability and credit ceiling; check the same account’s identity, balance and established budget. Obtain one scene prompt, a 5–15-second integer duration and an explicit 480P or 768P choice. Set model to MiniMax-H3-Max-Turbo. For text alone, specify a supported concrete ratio instead of adaptive. If frame images are requested, use first_frame and add last_frame only with a first frame; the image controls the aspect ratio. Do not add reference-image/video/audio items. Check the image format, dimensions and size, and prefer public HTTPS image URLs over large embedded data. Submit only the user’s authorized generation with one saved idempotency key and maxCredits within budget. If submission is uncertain, recover that same run instead of making another paid request. Preserve the actual completion status and missing fields; save the video from the returned link promptly, report its settings and the confirmed charge. Model naming alone does not establish generation speed or quality.

Task:
Turn this idea into a short video: [a yellow leaf drifting along a quiet stream]. Have the camera [follow the leaf slowly]. Make the video [5 seconds] long, [wide screen], with [standard picture quality].

Paste into your connected AI's conversation.

Connection guide

Up to 0.72 credits / call

The final charge is based on confirmed usage. Unused reserved credits return to your available balance.

MiniMax

AI Text to Video Generator · MiniMax H3 Max Turbo

You receive

Provide one nonempty scene prompt, MiniMax-H3-Max-Turbo, 480P or 768P and a 5–15-second duration to generate a short video and retrieve its file from the returned link. Use a concrete ratio for text alone, or supply a first-frame image with an optional paired last frame. Keep the task status and returned video settings with the file.

Start with your task

Turn this idea into a short video: [a yellow leaf drifting along a quiet stream]. Have the camera [follow the leaf slowly]. Make the video [5 seconds] long, [wide screen], with [standard picture quality].

What to know

A last frame must accompany a first frame; reference-image, reference-video and reference-audio inputs are unavailable. Frame formats, dimensions and size must meet the current requirements. Save the video promptly because its download link is time limited.

Inputs & outputs

Inspect the current inputs, availability, and maximum charge before starting.

Input schema

Input schema
Field / Path	Type	Requirement	Meaning
Video-generation inputs`body`	`object`	Required	Required object carrying the fixed model, scene content, selected resolution and duration, plus any mode-specific ratio or frame images. Required fields `model, content, resolution, duration`
Generation model`body.model`	`string`	Required	Specifies the model for this video request; the required string is MiniMax-H3-Max-Turbo. Fixed value `MiniMax-H3-Max-Turbo`
Video aspect ratio`body.ratio`	`string`	Optional	Choose adaptive, 21:9, 16:9, 4:3, 1:1, 3:4 or 9:16. Text-only video requires an explicit value other than adaptive. With frame images, the image decides the ratio and the request resolves to adaptive. Options `adaptive, 21:9, 16:9, 4:3, 1:1, 3:4, 9:16`
Prompt and frame items`body.content`	`array`	Required	Required list containing exactly one nonempty text item, optionally with first-frame and paired last-frame image items. Reference image, video and audio items are not supported. Minimum items `1`
[]`body.content[]`	`object`	—
Scene prompt`body.content[].text`oneOf · 1	`string`	—	Required on the one text item: 1–7,000 characters describing the desired scene or motion. Frame images do not remove the text requirement. Minimum length `1` Maximum length `7000`
Item kind`body.content[].type`oneOf · 1	`string`	—	The required tag is text for the scene description or image_url for a frame image. These are the two declared content branches. Fixed value `text`
Frame position`body.content[].role`oneOf · 2	`string`	—	Use first_frame for the opening image or last_frame for an ending image paired with a first frame. A single image with no role is treated as first_frame; reference_image is not an accepted role. Options `first_frame, last_frame`
Item kind`body.content[].type`oneOf · 2	`string`	—	The required tag is text for the scene description or image_url for a frame image. These are the two declared content branches. Fixed value `image_url`
Frame image source`body.content[].image_url`oneOf · 2	`object`	—	Required object on an image_url item. Its url provides the image used at the frame position selected by role. Required fields `url`
Frame image address`body.content[].image_url.url`oneOf · 2	`string`	—	Nonempty public HTTPS URL or data URI; prefer HTTPS for large images. Supports JPG/JPEG/PNG/WEBP/HEIC/HEIF, at most 30 MB per image, 256–5,760 pixels per side and width-to-height ratio 0.4–2.5. mm_file:// is unavailable. Minimum length `1`
Requested clip length`body.duration`	`integer`	Required	Whole-number output length in seconds, required from 5 through 15. This is a requested generation setting, separate from the confirmed charge. Minimum `5` Maximum `15`
Generated-video resolution`body.resolution`	`string`	Required	Required choice of 480P or 768P for the output video. There is no preset resolution; choose it explicitly. Options `480P, 768P`

View raw JSON

{
  "type": "object",
  "required": [
    "body"
  ],
  "properties": {
    "body": {
      "type": "object",
      "$schema": "https://json-schema.org/draft/2020-12/schema",
      "required": [
        "model",
        "content",
        "resolution",
        "duration"
      ],
      "~standard": {
        "vendor": "zod",
        "version": 1,
        "jsonSchema": {}
      },
      "properties": {
        "model": {
          "type": "string",
          "const": "MiniMax-H3-Max-Turbo",
          "description": "Fixed to MiniMax-H3-Max-Turbo. Required."
        },
        "ratio": {
          "enum": [
            "adaptive",
            "21:9",
            "16:9",
            "4:3",
            "1:1",
            "3:4",
            "9:16"
          ],
          "type": "string",
          "description": "Aspect ratio. REQUIRED and must not be adaptive for text-to-video. Image-to-video always resolves to adaptive (the input image decides)."
        },
        "content": {
          "type": "array",
          "items": {
            "oneOf": [
              {
                "type": "object",
                "required": [
                  "type",
                  "text"
                ],
                "properties": {
                  "text": {
                    "type": "string",
                    "maxLength": 7000,
                    "minLength": 1,
                    "description": "Prompt describing the video (max 7000 characters). REQUIRED in every request, in every scenario."
                  },
                  "type": {
                    "type": "string",
                    "const": "text"
                  }
                },
                "additionalProperties": false
              },
              {
                "type": "object",
                "required": [
                  "type",
                  "image_url"
                ],
                "properties": {
                  "role": {
                    "enum": [
                      "first_frame",
                      "last_frame"
                    ],
                    "type": "string",
                    "description": "first_frame (default when a single image carries no role), last_frame (must be paired with first_frame). Formats: JPG, JPEG, PNG, WEBP, HEIC, HEIF; 256-5760px per side; aspect ratio 0.4-2.5."
                  },
                  "type": {
                    "type": "string",
                    "const": "image_url"
                  },
                  "image_url": {
                    "type": "object",
                    "required": [
                      "url"
                    ],
                    "properties": {
                      "url": {
                        "type": "string",
                        "minLength": 1,
                        "description": "Public HTTPS URL, or a data: URI (data:image/jpeg;base64,...). MiniMax mm_file:// references are not supported. Limits: image <=30MB, reference video <=50MB, reference audio <=15MB, whole request body <=64MB — prefer URLs over data: URIs for video."
                      }
                    },
                    "additionalProperties": false
                  }
                },
                "additionalProperties": false
              }
            ]
          },
          "minItems": 1,
          "description": "Multimodal input. Every request needs exactly one non-empty text item. Add first_frame/last_frame images for image-to-video. Reference images, video and audio are not supported on this model."
        },
        "duration": {
          "type": "integer",
          "maximum": 15,
          "minimum": 5,
          "description": "Output length in seconds, 5-15."
        },
        "resolution": {
          "enum": [
            "480P",
            "768P"
          ],
          "type": "string",
          "description": "Output resolution. Drives the per-second rate: 480P $0.025/s, 768P $0.04/s. The USD amounts in this input description are upstream supplier values; Toolmu charges the current catalog credits."
        }
      },
      "additionalProperties": false
    }
  },
  "additionalProperties": false
}

Result schema

Output fields have not been documented yet.

Additional notes

Text describes the requested scene and motion in both supported modes. With no frame image, choose an explicit width-to-height ratio. When an image is used as first_frame, its aspect ratio controls the image-to-video request.

Use a first_frame image to set the starting scene and a paired last_frame image to supply an ending boundary for the requested motion. Both still need one text prompt. These frame positions guide the generation; they are not standalone reference-image inputs or a promise of exact pixel matching.

The returned task identifies the video-generation request. Its supplier task ID is separate from the Toolmu run ID; succeeded marks completion, and content.url provides the video for retrieval and saving. MiniMax defines this as a time-limited download link, so save the file promptly.

Returned model, resolution, duration and ratio describe the video settings. MiniMax defines created_at and updated_at as Unix seconds for task creation and its latest status update. output_seconds records output video seconds; total_seconds records metered input plus output seconds, and input_image_count counts supplied frame images here. Preserve zero values. These usage measures are separate from the confirmed Toolmu credit charge.

MiniMax video task field definitions

Questions about this tool.

Inputs, results and details to know before running it.

Get connected

No. Supply a concrete supported aspect ratio such as 16:9 or 9:16. The image-to-video mode instead follows the frame image’s ratio and resolves to adaptive.

AI Text to Video Generator · MiniMax H3 Max Turbo

AI Text to Video Generator · MiniMax H3 Max Turbo

You receive

Start with your task

What to know

Inputs & outputs

Input schema

Result schema

Describe one simple scene

Choose the length and picture options

Save the finished video

Questions about this tool.

You receive

Start with your task

What to know

Inputs & outputs

Input schema

Result schema

Describe one simple scene

Choose the length and picture options

Save the finished video

Questions about this tool.

Can I use adaptive with text alone?

Can the last frame be used without a first frame?

Can I guide it with a video or an audio clip?

Does the model name promise faster completion?